Seeing Further on the Shoulders of Giants: Knowledge Inheritance for Vision Foundation Models

• URL: http://arxiv.org/abs/2508.14707v1
• Date: Wed, 20 Aug 2025 13:30:23 GMT
• Title: Seeing Further on the Shoulders of Giants: Knowledge Inheritance for Vision Foundation Models
• Authors: Jiabo Huang, Chen Chen, Lingjuan Lyu,
• Abstract summary: Vision foundation models (VFMs) are predominantly developed using data-centric methods.<n>Many open-source vision models have been pretrained on domain-specific data.<n>We present a new model-driven approach for training VFMs through joint knowledge transfer and preservation.
• Score: 43.517843843279266
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Vision foundation models (VFMs) are predominantly developed using data-centric methods. These methods require training on vast amounts of data usually with high-quality labels, which poses a bottleneck for most institutions that lack both large-scale data and high-end GPUs. On the other hand, many open-source vision models have been pretrained on domain-specific data, enabling them to distill and represent core knowledge in a form that is transferable across diverse applications. Even though these models are highly valuable assets, they remain largely under-explored in empowering the development of a general-purpose VFM. In this paper, we presents a new model-driven approach for training VFMs through joint knowledge transfer and preservation. Our method unifies multiple pre-trained teacher models in a shared latent space to mitigate the ``imbalanced transfer'' issue caused by their distributional gaps. Besides, we introduce a knowledge preservation strategy to take a general-purpose teacher as a knowledge base for integrating knowledge from the remaining purpose-specific teachers using an adapter module. By unifying and aggregating existing models, we build a powerful VFM to inherit teachers' expertise without needing to train on a large amount of labeled data. Our model not only provides generalizable visual features, but also inherently supports multiple downstream tasks. Extensive experiments demonstrate that our VFM outperforms existing data-centric models across four fundamental vision tasks, including image classification, object detection, semantic and instance segmentation.

Related papers

• UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models [62.76435672183968]
  We introduce a novel framework, namely UNIFORM, for knowledge transfer from a diverse set of off-the-shelf models into one student model.<n>We propose a dedicated voting mechanism to capture the consensus of knowledge both at the logit level and at the feature level.<n>Experiments demonstrate that UNIFORM effectively enhances unsupervised object recognition performance compared to strong knowledge transfer baselines.
  arXiv  Detail & Related papers  (2025-08-27T00:56:11Z)
• Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning [79.46570165281084]
  We propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks.
  arXiv  Detail & Related papers  (2024-11-11T07:36:19Z)
• Specialized Foundation Models Struggle to Beat Supervised Baselines [60.23386520331143]
  We look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow.<n>We find that it is consistently possible to train simple supervised models that match or even outperform the latest foundation models.
  arXiv  Detail & Related papers  (2024-11-05T04:10:59Z)
• Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT [0.5999777817331317]
  This work tries to leverage one such foundation model, called DINOv2, through using knowledge distillation. The results imply that although the proposed method shows improvements in certain scenarios, it does not consistently outperform the original FairMOT model.
  arXiv  Detail & Related papers  (2024-07-25T14:21:35Z)
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
  We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other. We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
  arXiv  Detail & Related papers  (2023-10-26T17:59:46Z)
• Learning from models beyond fine-tuning [78.20895343699658]
  Learn From Model (LFM) focuses on the research, modification, and design of foundation models (FM) based on the model interface.<n>The study of LFM techniques can be broadly categorized into five major areas: model tuning, model distillation, model reuse, meta learning and model editing.<n>This paper gives a comprehensive review of the current methods based on FM from the perspective of LFM.
  arXiv  Detail & Related papers  (2023-10-12T10:20:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.